Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable context beyond these: it explains the output is a 'record view using the authenticated API normalized data shape (schemaVersion 2)', that consent and sync are simulated with no usable change cursor, and that empty categories describe the fixture only. It also clarifies that behavior scenarios (rate-limited, consent-revoked, etc.) produce scripted errors or partial results. This is rich behavioral disclosure that complements, not contradicts, the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact—three sentences that front-load the core purpose and usage guidance, followed by critical behavioral caveats. Every sentence earns its place: the first explains what it does and why to prefer it; the second describes the output shape; the third covers fixture and behavior notes. There is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (so return values are defined there), the description thoroughly covers what an agent needs to call it correctly: the ability to request multiple categories, the scenario picker, the simulated behavior, and the absence of a change cursor. It addresses the key constraints (fictional patients, consent/sync simulation) and clarifies edge cases (empty categories, behavior scenarios). Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50%: the 'scenario' parameter has a description, but 'categories' does not. The description compensates by listing the category types (demographics, medications, conditions, labs, vitals, allergies, immunizations, encounters) and implying the 'mix' concept, though it omits 'documents' and 'claims' from the wording even though they appear in the enum. The 'scenario' meaning is covered explicitly ('pick one with scenario', with behavior scenarios noted). Given the partial schema coverage and the added clarity about scenario selection, the description goes beyond the schema but stops short of fully matching the enum list, so a 4 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Get') with a clear resource ('any mix of demographics, medications, conditions, labs, vitals, allergies, immunizations, encounters') and explicitly differentiates from sibling single-category tools ('prefer this over several single-category tools'). It goes beyond a generic statement by naming the data shape (schemaVersion 2) and the fictional-patient constraint. An agent can immediately tell what this tool does and how it relates to the other get_demo_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to prefer this over single-category tools when multiple categories are needed. It also instructs to 'pick one with scenario' and warns about simulated consent/sync and lack of a change cursor. It names the alternative (single-category tools) and provides clear conditions for use. This is explicit, actionable guidance that eliminates ambiguity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.